Abstract
The administrative burden in routine healthcare processes is high, but for communication among care providers the reporting about patient consultations is very essential. In order to reduce this burden we have started the Care2Report research program (www.care2report.nl) that aims at a automated medical reporting based on multimodal (audio, video, bleutooth) recording of a consultation, followed by knowledge representation, ontological conversation interpretation, and finally the generation and uploading of the report in the electronic medical record system. In this keynote I will present the aims and goals of the Care2Report research program, the various linguistic intelligence pipelines, its current functional and technical architecture, and the achievements so far. The linguistic pipeline research will be illustrated by (i) a generic method for the design of trusted cloud pipelines in medical reporting, (ii) the generation of medical guideline ontologies for the matching of the consultation audio transcript, and (iii) the automated pseudonimisation of privacy related data by means of named entity recognition. We end with an outlook of the current research projects and experiments in healthcare institutions.
Paper Type
Keynote Presentation
DOI
10.62036/ISD.2022.37
Reducing the Administrative Burden in Healthcare: Speech and Action Recognition for Automated Medical Reporting
The administrative burden in routine healthcare processes is high, but for communication among care providers the reporting about patient consultations is very essential. In order to reduce this burden we have started the Care2Report research program (www.care2report.nl) that aims at a automated medical reporting based on multimodal (audio, video, bleutooth) recording of a consultation, followed by knowledge representation, ontological conversation interpretation, and finally the generation and uploading of the report in the electronic medical record system. In this keynote I will present the aims and goals of the Care2Report research program, the various linguistic intelligence pipelines, its current functional and technical architecture, and the achievements so far. The linguistic pipeline research will be illustrated by (i) a generic method for the design of trusted cloud pipelines in medical reporting, (ii) the generation of medical guideline ontologies for the matching of the consultation audio transcript, and (iii) the automated pseudonimisation of privacy related data by means of named entity recognition. We end with an outlook of the current research projects and experiments in healthcare institutions.
Recommended Citation
Brinkkemper, S. (2022). Reducing the Administrative Burden in Healthcare: Speech and Action Recognition for Automated Medical Reporting. In R. A. Buchmann, G. C. Silaghi, D. Bufnea, V. Niculescu, G. Czibula, C. Barry, M. Lang, H. Linger, & C. Schneider (Eds.), Information Systems Development: Artificial Intelligence for Information Systems Development and Operations (ISD2022 Proceedings). Cluj-Napoca, Romania: Risoprint. ISBN: 978-973-53-2917-4. https://doi.org/10.62036/ISD.2022.37